Instructions to use alecsharpie/codegen_350m_html with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alecsharpie/codegen_350m_html with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="alecsharpie/codegen_350m_html")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("alecsharpie/codegen_350m_html")
model = AutoModelForCausalLM.from_pretrained("alecsharpie/codegen_350m_html")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use alecsharpie/codegen_350m_html with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alecsharpie/codegen_350m_html"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alecsharpie/codegen_350m_html",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/alecsharpie/codegen_350m_html

SGLang

How to use alecsharpie/codegen_350m_html with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "alecsharpie/codegen_350m_html" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alecsharpie/codegen_350m_html",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "alecsharpie/codegen_350m_html" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alecsharpie/codegen_350m_html",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use alecsharpie/codegen_350m_html with Docker Model Runner:
```
docker model run hf.co/alecsharpie/codegen_350m_html
```

Finetuning script/method

by ahmedghani - opened Dec 10, 2022

Discussion

ahmedghani

Dec 10, 2022

Hi @alecsharpie , it is awesome to see that you finetuned CodeGen on The-stack I am doing the same but for 15 languages and on 16B model. I actually wanna know the training methods you used and if you are willing to share your training script with me so that it can be helpful for me as well. Thanks.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment